Add getCommandDiagnostics and getShortcutDiagnostics mocks to fix
'Cannot read properties of undefined' errors in InteractiveMode tests.
regression from 32a305cb
Bypass the Anthropic SDK streaming parser entirely. Use
client.messages.create().asResponse() and decode the SSE stream
ourselves with defensive JSON parsing that repairs invalid escape
sequences and control characters inside string literals.
- Switch from SDK .stream() to .asResponse() + pi-owned SSE decoder
- Add repairJson() / parseJsonWithRepair() to json-parse.ts
- Add anthropic-sse-parsing.test.ts regression for malformed tool deltas
- Update github-copilot-anthropic.test.ts mock to match new call path
- Update deprecated claude-3-5-haiku-20241022 refs to claude-haiku-4-5
- Remove stale non-reasoning model test
fixes#3175
promptGuidelines bullets are appended flat to the Guidelines section
with no tool name prefix. Using 'Use this tool when...' is ambiguous
because the LLM cannot tell which tool 'this' refers to. Updated docs
and examples to use explicit tool names instead.
Rename BUILTIN_TOOLS to TEMPLATE_RENDERED_TOOLS to match what the set
actually represents: tools rendered directly by the HTML template instead of
pre-rendered through the TUI→ANSI→HTML pipeline.
Move grep and find off the template-rendered exclusion path so they use their
existing TUI renderCall/renderResult output in HTML export.
Add a dedicated HTML renderer for ls and keep it in the template-rendered set.
Unlike grep and find, rendering ls through the terminal-oriented Text component
introduced spacing artifacts in exported HTML due to full-width line padding,
so ls is rendered natively in the export template instead.
- treat tools as a global allowlist across built-in, extension, and SDK tools
- remove process-cwd singleton tool usage from SDK and CLI paths
- add regression coverage for extension tool filtering
closes#3452closes#2835
Some models (Opus 4.6, GLM-5.1) send the edits parameter as a JSON
string instead of a parsed array. This fails AJV validation with
'must be array' and models fall back to sed/python.
Parse stringified edits in prepareEditArguments before validation.
* feat(agent,coding-agent): add per-tool executionMode field to AgentTool and ToolDefinition
Add optional executionMode?: ToolExecutionMode to AgentTool and
ToolDefinition interfaces. Propagate through wrapToolDefinition and
createToolDefinitionFromAgentTool. No behavioral change yet — agent
loop will read this field in a follow-up.
* feat(agent): support per-tool executionMode override for sequential execution
When a tool defines executionMode='sequential', the agent loop
forces sequential execution of all tool calls in that batch,
even if the global config is parallel.
* feat(coding-agent): re-export ToolExecutionMode from @mariozechner/pi-agent-core
Makes the type available to extensions that want to set
executionMode on tool definitions.
* feat(coding-agent): add tic-tac-toe extension example with executionMode: sequential
Demonstrates per-tool executionMode: the agent plays via move/play
tool calls that share a cursor. Without sequential execution, play
can resolve before earlier moves finish, landing on the wrong cell.
